dictation
Warn
Audited by Snyk on Aug 6, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (medium risk: 0.30). The Dictation skill runtime only ingests the user-provided argument text that follows an explicit skill invocation (“Read the argument text that follows the explicit skill invocation”), and it processes whatever the user dictates within the conversation.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata